Data as of October 25, 2026 · How the score is built
GPT Realtime 2.1 Mini
Decision readingGPT Realtime 2.1 Mini is tracked, but not publicly ranked yet. Published speech or voice results from EVA-Bench appear below. They do not produce a weighted text-model score.
Released Jul 6, 2026 — see all recent releases
Voice benchmark evidence
EVA-Bench is an owner-defined voice evaluation. Its result stays separate from BenchLM's weighted text-model ranking.
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- gpt-realtime-2.1-miniOpenAI GPT Realtime 2.1 Mini model documentation
- Context window
- 128KOpenAI GPT Realtime 2.1 Mini model documentation
- Maximum output
- Not sourced yet
- Knowledge cutoff
- September 30, 2024OpenAI GPT Realtime 2.1 Mini model documentation
- Input modalities
- text, audio, imageOpenAI GPT Realtime 2.1 Mini model documentation
- Output modalities
- text, audioOpenAI GPT Realtime 2.1 Mini model documentation
- Parameters
- Not disclosed by the provider
- Availability
- OpenAI APIOpenAI GPT Realtime 2.1 Mini model documentation
- Cloud regions
- Not tracked yet
- Lifecycle
- activeOpenAI GPT Realtime 2.1 Mini model documentation
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Published at $0.060 per million cached input tokensOpenAI model documentation
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track GPT Realtime 2.1 Mini, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
GPT Realtime 2.1 Mini is a proprietary model with a 128K context window. No explicit reasoning mode is documented in this profile.
Available on the OpenAI Realtime API as gpt-realtime-2.1-mini since July 6, 2026, with text, audio, and image input, text and audio output, a 128,000-token context, 32,000-token maximum output, function calling, and prompt caching.
GPT Realtime 2.1 Mini is a display-only distilled speech-to-speech reasoning model for lower-cost voice agents on the Realtime API. Voice-protocol results remain separate from BenchLM’s weighted text-model ranking.
Speech or voice evidence appears above; text-model benchmark coverage remains empty.
Last updated October 25, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does GPT Realtime 2.1 Mini perform overall in AI benchmarks?
GPT Realtime 2.1 Mini has published speech or voice results in EVA-Bench. Those results remain separate from the weighted text-model ranking, so this profile does not assign a BenchLM score or overall rank. Use the linked evaluation's metric and run conditions to compare speech systems.
Does GPT Realtime 2.1 Mini have full benchmark coverage on BenchLM?
No. GPT Realtime 2.1 Mini's speech or voice results appear in EVA-Bench, but it has no published text-model benchmark rows. The voice evaluation does not fill the text-model coverage slots or produce an overall rank. Missing text coverage is not treated as a zero score.
What is the context window size of GPT Realtime 2.1 Mini?
GPT Realtime 2.1 Mini has a documented context window of 128K. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.